{"total":28,"rows":[{"id":"2303.03915","title":"The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset","created":"2023-03-07","cited_by_count":148,"area":null},{"id":"2301.13126","title":"LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain","created":"2023-01-30","cited_by_count":68,"area":null},{"id":"2307.01370","title":"Multilingual Language Models are not Multicultural: A Case Study in Emotion","created":"2023-07-03","cited_by_count":54,"area":null},{"id":"2309.07755","title":"Generative AI Text Classification using Ensemble LLM Approaches","created":"2023-09-14","cited_by_count":29,"area":null},{"id":"2212.05129","title":"Measuring Data","created":"2022-12-09","cited_by_count":18,"area":null},{"id":"2307.05410","title":"BLUEX: A benchmark based on Brazilian Leading Universities Entrance eXams","created":"2023-07-11","cited_by_count":15,"area":null},{"id":"2402.11192","title":"I Learn Better If You Speak My Language: Understanding the Superior Performance of Fine-Tuning Large Language Models with LLM-Generated Responses","created":"2024-02-17","cited_by_count":15,"area":null},{"id":"2305.20080","title":"Findings of the VarDial Evaluation Campaign 2023","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2210.00465","title":"Assessing the impact of contextual information in hate speech detection","created":"2022-10-02","cited_by_count":10,"area":null},{"id":"2212.08390","title":"Lessons learned from the evaluation of Spanish Language Models","created":"2022-12-16","cited_by_count":8,"area":null},{"id":"2412.09460","title":"The Impact of Copyrighted Material on Large Language Models: A Norwegian Perspective","created":"2024-12-12","cited_by_count":8,"area":null},{"id":"2402.14458","title":"NLAS-multi: A Multilingual Corpus of Automatically Generated Natural Language Argumentation Schemes","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2303.03487","title":"Two-stage Pipeline for Multilingual Dialect Detection","created":"2023-03-06","cited_by_count":3,"area":null},{"id":"2403.15362","title":"CoLLEGe: Concept Embedding Generation for Large Language Models","created":"2024-03-22","cited_by_count":3,"area":null},{"id":"2407.10745","title":"What distinguishes conspiracy from critical narratives? A computational analysis of oppositional discourse","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2309.11259","title":"Sequence-to-Sequence Spanish Pre-trained Language Models","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2310.07135","title":"Comparing Styles across Languages: A Cross-Cultural Exploration of Politeness","created":"2023-10-11","cited_by_count":2,"area":null},{"id":"2507.00999","title":"La Leaderboard: A Large Language Model Leaderboard for Spanish Varieties and Languages of Spain and Latin America","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2604.04704","title":"IDIOLEX: Unified and Continuous Representations for Idiolectal and Stylistic Variation","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2208.13947","title":"A Spanish dataset for Targeted Sentiment Analysis of political headlines","created":"2022-08-30","cited_by_count":1,"area":null},{"id":"2410.11540","title":"Data Quality Control in Federated Instruction-tuning of Large Language Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2502.11779","title":"Efficient Response Generation Strategy Selection for Fine-Tuning Large Language Models Through Self-Aligned Perplexity","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2306.01325","title":"LyricSIM: A novel Dataset and Benchmark for Similarity Detection in Spanish Song LyricS","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2410.00616","title":"Detecci\\'on Autom\\'atica de Patolog\\'ias en Notas Cl\\'inicas en Espa\\~nol Combinando Modelos de Lenguaje y Ontolog\\'ias M\\'edicos","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2412.03176","title":"Automatic detection of diseases in Spanish clinical notes combining medical language models and ontologies","created":"2024-12-04","cited_by_count":0,"area":null},{"id":"2509.24908","title":"BOE-XSUM: Extreme Summarization in Clear Language of Spanish Legal Decrees and Notifications","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2605.12906","title":"Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2608.22452","title":"From Exposure to Expectation: Frequency, Surprisal, and Language Across Development in Spanish","created":"2026-08-23","cited_by_count":0,"area":null}],"next_cursor":null}